Python-爬虫-懒得写的部分

sunzhihaofuture 2020-06-10

requests

#!/usr/bin/env python3
# -*- coding: utf-8 -*-

import requests
import re

url = ""
hd = {"User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:75.0) Gecko/20100101 Firefox/75.0",}
px = {"http":"http://127.0.0.1:8888"} # 代理
rst = requests.get(url, headers = hd) 

title = re.compile("<title>(.*?)</title>", re.S).findall(rst.text)

urllib

#!/usr/bin/env python3
# -*- coding: utf-8 -*-

import urllib
import urllib.request
import re
import random

# 浏览器伪装
opener = urllib.request.build_opener()
UA = ("User-Agent", "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.162 Safari/537.36")
opener.addheaders = [UA]
urllib.request.install_opener(opener)

url = ""
data = urllib.request.urlopen(url).read().decode(‘utf-8‘, ‘ignore‘)

# 构建用户代理池
uapools=[
    "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.162 Safari/537.36"
    "Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:75.0) Gecko/20100101 Firefox/75.0"
    ""
]

def UA():
    opener = urllib.request.build_opener()
    thisua = random.choice(uapools)
    ua = ("User-Agent", thisua)
    opener.add_handlers = [ua]
    urllib.request.install_opener(opener)
    # print("当前使用UA:" + str(thisua))
    
for i in range(0, 10):
    UA()
    data = urllib.request.urlopen(url).read().decode(‘utf-8‘, ‘ignore‘)

范例

#!/usr/bin/env python3
# -*- coding: utf-8 -*-

import urllib.request
import re
import random
import time

uapools = [
    "Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:75.0) Gecko/20100101 Firefox/75.0",
    "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.162 Safari/537.36"
]

def UA():
    opener = urllib.request.build_opener()
    thisua = random.choice(uapools)
    ua = ("User-Agent", thisua)
    opener.addheaders = [ua]
    urllib.request.install_opener(opener)
    print("当前使用UA: " + str(thisua))

for i in range(0, 35): # 总页数
    UA()
    thisurl = "" # 构建 url
    try:
        data = urllib.request.urlopen(thisurl).read().decode(‘utf-8‘, ‘ignore‘)
        pat = ‘‘ # 构建正则
        rst = re.compile(pat, re.S).findall(data)
        for j in range(0, len(rst)):  # 打印
            print(rst[j])
            print("------")
    except Exception as err:
        pass

相关推荐